This paper advances research on social networks, extended reality, and the metaverse by bringing together innovations from two different communities – AI and cognitive science – to develop LLM-based agents with not only fluent responses but also realistic opinion dynamics that capture a variety of human biases, imperfections, and general departures from rationality. This avenue of investigation can empower applications from social simulation of human opinions in geopolitical hotspots to realistic non-player character interactions in metaverse games. Recent advances in AI have made remarkable progress toward general intelligence with the introduction of large language models (LLMs). They also enabled grounding LLM responses in specialized information stored externally using retrieval-augmented generation (RAG). In a separate line of research, studies on human cognition have produced cognitive architectures that emulate human departures from rationality, such as biases and imperfections, which are crucial to understanding a wide range of social phenomena and human preferences. A critical mechanism in cognitive architectures is the modulation of retrieval weights from (human) memory; we are biased in what we remember. Combining RAG with cognitive model-inspired computation of information retrieval weights, we develop the Irrational LLM – one that weighs information retrieval in RAG systems according to cognitive models, thereby accurately emulating human opinion formation. We implement the novel human cognition-inspired RAG framework (CogRAG) and use it to emulate option developments on different sides of a conflict regarding debated issues. Responses generated by CogRAG (on posts withheld from training data) show close correspondence with real responses posted on social media, suggesting the viability of this approach in approximating biased human opinions. We hope this study paves the way to new directions in AI, social networks, metaverse computing, and human-in-the-loop modeling that better represent diverse human opinions in geopolitical, entertainment, and socio-technical contexts.

This paper addresses the problem of optimizing the allocation of labeling resources to enhance the performance of semi-supervised belief representation learning in social networks. The objective is to strategically identify valuable nodes in social media graphs that are worth labeling within a constrained budget to maximize downstream learning task performance. Despite progress in unsupervised and semi-supervised methods for belief and ideology representation learning on social networks, the scarcity of high-quality labeled social data continues to pose a significant challenge. Therefore, allocating labeling efforts judiciously becomes critical in scenarios with limited resources for labeling. This paper introduces a perturbation-based active learning strategy inspired by graph augmentation, PerbALGraph, which progressively selects nodes for labeling using an automatic estimator, thereby eliminating the need for human guidance. This estimator is based on the principle that nodes in the network that exhibit heightened sensitivity to changes in structural features are better candidates for labeling. We design the estimator to be model-agnostic and application-independent and to score candidates under a set of designed graph perturbations. Extensive experiments on six real-world social media datasets demonstrate the superior performance and robustness of our proposed method compared to existing active learning approaches.

The rise of multi-modal, multi-node foundation models has revolutionized intelligent IoT sensing systems by enabling general-purpose inference from distributed sensing sources to support diverse downstream applications. However, the high communication cost of transmitting raw sensor data from distributed nodes to a central inference model remains a critical bottleneck, particularly in bandwidth- or energy-constrained environments. While existing compression methods can reduce data volume, they often lack the adaptability needed to handle variations in data relevance and redundancy across sources, modalities, and time. To address this challenge, we introduce ZipFM, a lightweight, plug-and-play middleware that dynamically configures sensor data compression strategies on a per-node, per-modality, and per-time-step basis to minimize network traffic while preventing model degradation, taking model sensitivity to different data sources into account. ZipFM is (i) compatible with different pre-trained foundation models without requiring access to their internal mechanisms or retraining, (ii) agnostic to the underlying tools available for data compression, and (iii) independent of the specific downstream inference tasks performed. At its core, ZipFM uses the compression-induced latent representation shift, produced by the foundation model's backbone, as a proxy for downstream accuracy degradation, and enforces a system-wide optimal representation shift (in the sense of minimizing compression-related degradation) through a lightweight feedback control mechanism. Experiments on three real-world IoT sensing datasets demonstrate that ZipFM significantly reduces communication costs while preserving model performance.

This paper introduces SCRAG, a prediction frame-work inspired by social computing, designed to forecast community responses to real or hypothetical social media posts. SCRAG can be used by public relations specialists (e.g., to craft messaging in ways that avoid unintended misinterpretations) or public figures and influencers (e.g., to anticipate social responses), among other applications related to public sentiment prediction, crisis management, and social what-if analysis. While large language models (LLMs) have achieved remarkable success in generating coherent and contextually rich text, their reliance on static training data and susceptibility to hallucinations limit their effectiveness at response forecasting in dynamic social media environments. SCRAG overcomes these challenges by integrating LLMs with a Retrieval-Augmented Generation (RAG) technique rooted in social computing. Specifically, our framework retrieves (i) historical responses from the target community to capture their ideological, semantic, and emotional makeup, and (ii) external knowledge from sources such as news articles to inject time-sensitive context. This information is then jointly used to forecast the responses of the target community to new posts or narratives. Extensive experiments across six scenarios on the X platform (formerly Twitter), tested with various embedding models and LLMs, demonstrate over 10% improvements on average in key evaluation metrics. A concrete example further shows its effectiveness in capturing diverse ideologies and nuances. Our work provides a social computing tool for applications where accurate and concrete insights into community responses are crucial.

Biometric features are quite suitable for identity authentication due to its inherent properties – universality, uniqueness and persistence. In fact, biometric authentication has been widely used in our daily life, especially in mobile devices. However, biometric features are quite sensitive, and once a feature is leaked to an evil adversary, it cannot be used in authentication any more. This leads to a push on research of biometric privacy protection. In this paper, we propose a face-based authentication system with the help of a computational secure sketch. The computational secure sketch takes charge of error tolerance on the face samplings. Then the face features of the same user are used to extract an authentication key, which is in turn used to do the identity authentication for the user. The computational security of the computational secure sketch makes sure that the public information obtained by the adversary does not affect the pseudorandomness of the authentication key, hence the privacy of face features is guaranteed. Moreover, the privacy protection technique in our face-based authentication system can be extended to other biometric-based authentication.